An image quality evaluation method, device, equipment, medium and product

Abstract

This invention discloses an image quality evaluation method, apparatus, device, medium, and product. The method includes: acquiring a road segment image; analyzing pixels in the road segment image to determine an overall image quality evaluation value; determining overall image weather information corresponding to the road segment image using a weather recognition model, wherein the overall image weather information indicates the weather conditions corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image; and determining an evaluation result based on the overall image quality evaluation value and the overall image weather information. The technical solution of this invention improves the accuracy of image quality evaluation by recognizing the overall image quality evaluation value and weather information in an image, and by evaluating image quality based on the overall image quality evaluation value and weather information, thereby providing a reference for subsequent road inspections.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to an image quality evaluation method, apparatus, device, medium, and product. Background Technology

[0002] Road patrol is a crucial step in ensuring road safety and smooth traffic flow. Vision-based road patrol technology can significantly improve patrol efficiency and has become a popular application. However, vision-based technologies rely heavily on image quality, especially in rainy or snowy weather, where image quality deteriorates severely and may cause the algorithm to malfunction.

[0003] Existing image quality assessment methods include objective methods, which evaluate image quality by calculating various metrics such as signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). These methods rely on the statistical characteristics of the image and can provide quantitative evaluation results. However, existing objective assessment methods mainly rely on statistical values ​​such as brightness and gradient of the image itself, which is not suitable for situations where road conditions are slightly degraded after light rain or snow, but the image quality itself is still good. They are not specifically tailored for road patrol scenarios. Summary of the Invention

[0004] This invention provides an image quality assessment method, apparatus, device, medium, and product to address the problem that image quality assessment is not specific to road patrol scenarios.

[0005] According to one aspect of the present invention, an image quality evaluation method is provided, comprising: Acquire road segment images; The pixels in the road segment image are analyzed to determine the overall image quality evaluation value; The weather recognition model determines the whole-map weather information corresponding to the road segment image, and the whole-map weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image; The evaluation result is determined based on the overall map quality evaluation value and the overall map weather information.

[0006] According to another aspect of the present invention, an image quality evaluation apparatus is provided, characterized in that it comprises: The acquisition module is used to acquire images of road segments; The whole image quality evaluation value determination module is used to analyze the pixels in the road segment image and determine the whole image quality evaluation value; The whole map weather information determination module is used to determine the whole map weather information corresponding to the road segment image through a weather recognition model. The whole map weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image. The evaluation result determination module is used to determine the evaluation result based on the overall map quality evaluation value and the overall map weather information.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method described in any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method described in any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the method described in any embodiment of the present invention.

[0010] The technical solution of this invention involves acquiring road segment images; analyzing the pixels in the road segment images to determine an overall image quality evaluation value; determining the overall image weather information corresponding to the road segment image using a weather recognition model, whereby the overall image weather information indicates the weather and road conditions of the road segment corresponding to the road segment image; and determining an evaluation result based on the overall image quality evaluation value and the overall image weather information. By determining the overall image quality evaluation value and the overall image weather information, which includes the weather and road conditions of the road segment image, the analysis is performed on the road condition scenarios of the road segment. This avoids the problem of inaccurate evaluation of road conditions due to poor road conditions but good image quality. By jointly evaluating road segment images based on the overall image weather information and the overall image quality evaluation value, the accuracy of image quality assessment is improved, thereby providing a reference for subsequent road inspections.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of an image quality evaluation method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of an image quality evaluation method provided in an embodiment of the present invention; Figure 3 This is a flowchart of an image quality evaluation method provided in Embodiment 2 of the present invention; Figure 4 This is a flowchart of an image quality evaluation method for sub-images provided in an embodiment of the present invention; Figure 5 This is a flowchart of another image quality evaluation method provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an image quality evaluation device provided in Embodiment 3 of the present invention; Figure 7 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] The acquisition, storage, use, and processing of data in the technical solution of this invention all comply with the relevant provisions of relevant laws and regulations.

[0017] Example 1 Figure 1 This is a flowchart of an image quality evaluation method provided in Embodiment 1 of the present invention. This embodiment is applicable to evaluating the image quality of road segments. The method can be executed by an image quality evaluation device, which can be implemented in hardware and / or software and can be configured in an electronic device. For example, the electronic device can be a computer, workstation, or server. Figure 1 As shown, the method includes: S110, Obtain road segment images.

[0018] In this embodiment, a road segment image can be understood as an image including the traffic segment to be inspected. The road segment image can be a grayscale image or a three-channel color image (Red, Green, Blue, RGB), and this invention is not limited thereto. The road segment image can be obtained through means such as road surveillance cameras, vehicle dashcams, or satellites. The road segment image may include, for example, road surface, road environment, timestamps, and real-time weather conditions.

[0019] Specifically, the process involves acquiring road segment images and uploading them to electronic devices via wired or wireless communication. The electronic devices then perform standardized processing on the road segment images, such as converting the format to a uniform format, encrypting and / or compressing them.

[0020] For example, after acquiring road segment images, the images are transmitted to electronic devices via a local area wireless network. The electronic devices then uniformly convert the road segment images from the original message format to grayscale image format. Before image quality evaluation, the electronic devices automatically perform initial screening on all acquired road segment images to filter out invalid or unusable images for subsequent analysis. Road segment images to be filtered out may include, for example: road segment images where the camera is obstructed, making the road segment invisible, or where the visible area accounts for less than a preset threshold; pure black or pure white road segment images; road segment images where the noise percentage exceeds a preset area threshold; and / or incomplete road segment images, etc.

[0021] S120. Analyze the pixels in the road segment image to determine the overall image quality evaluation value.

[0022] In this embodiment, the overall image quality evaluation value can be a quantitative evaluation result of the entire road segment image. The overall image quality evaluation value can be obtained by performing pixel-by-pixel analysis on the road segment image based on one or more preset image quality indicators or statistical measures of image quality indicators. For example, image indicators can be the sharpness, brightness, and / or contrast of the road segment image.

[0023] Specifically, the road segment image is analyzed pixel by pixel, the image quality index of each pixel is calculated, and the statistical value of the image quality index of each pixel is statistically analyzed. The statistical values ​​of each image quality index are weighted and summed to obtain the overall image quality evaluation value.

[0024] For example, when the image quality metrics are brightness and sharpness, the brightness and sharpness of each pixel in the road segment image can be calculated separately. Specifically, the brightness of each pixel in the road segment image can be determined by converting the road segment image into a grayscale image, defining the grayscale value of each pixel as the brightness, and then calculating the average brightness of each pixel in the road segment image. The sharpness of each pixel in the road segment image can be determined by calculating the gradient of each pixel in the horizontal and vertical directions using edge detection operators such as Sobel, and then calculating the average sharpness of each pixel in the road segment image. The weighted sum of the average brightness and the average sharpness yields the overall image quality evaluation value.

[0025] S130. Determine the overall weather information corresponding to the road segment image through a weather recognition model. The overall weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image.

[0026] In this embodiment, the weather recognition model can be a model used to identify the weather corresponding to a road segment image. The weather recognition model can be a neural network model. The overall image weather information can be understood as the weather information corresponding to the road segment image. The overall image weather information includes, but is not limited to, the real-time weather and / or the road conditions of the road segment corresponding to the road segment image. For example, the real-time weather can be sunny, cloudy, light rain, heavy rain, light snow, or heavy snow, etc., and the road conditions of the road segment can be such as dry, with snow accumulation, or with water accumulation, etc.

[0027] Specifically, the road segment image is input into the weather recognition model. The weather recognition model can determine the weather and road conditions corresponding to the road segment image based on factors such as the overall color tone, uniformity of illumination, and texture of the object surface. The judgment results (such as the confidence or probability of various weather and road conditions) are integrated and output in a specific format. The output result is the weather information of the whole image.

[0028] For example, road segment images are input into a weather recognition model. The weather recognition model determines the weather category based on the overall tone and illumination uniformity of the road segment images. It determines the road condition by judging whether the road surface is reflective and whether there are coverings. The probability or confidence level of the road segment images including each weather category, as well as the probability or confidence level of the road segment images including each road condition category, are integrated into a specific format, such as a matrix, and output as the weather information of the whole image.

[0029] S140. Determine the evaluation result based on the overall map quality evaluation value and the overall map weather information.

[0030] In this embodiment, the evaluation result can be the quantized evaluation result corresponding to the road segment image. The processing method for the traffic segment corresponding to the road segment image can be determined based on the numerical range of the evaluation result. For example, if the evaluation result is within a certain preset numerical range, the traffic segment corresponding to the road segment image can be considered to have good road conditions and does not require inspection.

[0031] Specifically, appropriate weights are assigned to the overall map quality evaluation value and the overall map weather information. The evaluation result is obtained by summing the weighted values ​​of the overall map quality evaluation value and the overall map weather information. Alternatively, the overall map quality evaluation value and the overall map weather information can be multiplied and the product is used as the evaluation result. Or, a neural network model can be used to fuse the overall map quality evaluation value and the overall map weather information to obtain the evaluation result. If the evaluation result is greater than a preset threshold, the evaluation result is reported.

[0032] For example, Figure 2 This is a flowchart of an image quality evaluation method provided by an embodiment of the present invention. First, road segment images are acquired. The image quality of the road segment images is evaluated using the overall image quality evaluation value. The road condition of the corresponding traffic segment is identified using the overall image weather information. The overall image quality evaluation value and the overall image weather information are fused. If the fused result is greater than a preset threshold, the result is reported.

[0033] The technical solution of this invention involves acquiring road segment images; analyzing the pixels in the road segment images to determine an overall image quality evaluation value; determining the overall image weather information corresponding to the road segment image using a weather recognition model, whereby the overall image weather information indicates the weather and road conditions of the road segment corresponding to the road segment image; and determining an evaluation result based on the overall image quality evaluation value and the overall image weather information. By determining the overall image quality evaluation value and the overall image weather information, which includes the weather and road conditions of the road segment image, the analysis is performed on the road condition scenarios of the road segment. This avoids the problem of inaccurate evaluation of road conditions due to poor road conditions but good image quality. By jointly evaluating road segment images based on the overall image weather information and the overall image quality evaluation value, the accuracy of image quality assessment is improved, thereby providing a reference for subsequent road inspections.

[0034] Example 2 Figure 3This is a flowchart of an image quality evaluation method provided in Embodiment 2 of the present invention. This embodiment is an optimization based on any of the above embodiments, and mainly includes a detailed description of the process for determining the overall image quality evaluation value, the process for determining the overall image weather information, the process for determining the evaluation result by combining confidence level, the mapping of the evaluation result, and the process for determining whether to report based on the evaluation result. It should be noted that technical details not described in detail in this embodiment can be found in any of the above embodiments. Figure 3 As shown, the method includes: S210, Obtain road segment images.

[0035] S220. Determine multiple image metrics of the road segment image.

[0036] In this embodiment, image metrics can be quantitative indicators describing the image quality of road segment images. Image metrics can be quantified image quality indicators and their corresponding statistics. Image metrics include, but are not limited to, average brightness, contrast, average gradient, and / or spectral distribution.

[0037] Specifically, the road segment images are analyzed pixel by pixel, and multiple image indicators are determined based on the brightness and variation patterns of each pixel in the road segment image.

[0038] For example, for a road segment image in RGB format, the image can be converted to grayscale, and the pixel value of each pixel in the grayscale image can be directly used as the brightness. Alternatively, a weight can be assigned to each color channel of the RGB image, and the sum of the products of each channel's pixel value and its corresponding weight can be used as the brightness. The average brightness can be determined by the ratio of the sum of the brightness of all pixels in the road segment image to the total number of pixels. The contrast can be obtained by dividing the difference between the maximum and minimum brightness values ​​by the sum of the maximum and minimum brightness values. The average gradient can be calculated as follows: first, calculate the sum of the squares of the first derivatives of all pixels in the road segment image in the horizontal and vertical directions; then, take the square root of this sum; finally, calculate the average of the square root of all pixels. The spectral distribution can be obtained by calculating the Fourier transform of the road segment image to obtain its spectrum, and then statistically analyzing the spectral distribution of the road segment image based on the spectrum.

[0039] S230. For each image index, determine the absolute error between the image index and the corresponding standard value, and determine the ratio of the absolute error to the corresponding standard value.

[0040] In this embodiment, the standard value can be a standard value corresponding to an image indicator. The standard value can be a quantitative evaluation standard for image quality. The standard value can be predetermined based on experience, or it can be determined based on business needs, scenarios, or industry standards; this invention does not impose any limitations on this.

[0041] Specifically, determine the standard value corresponding to each image indicator, calculate the absolute error between the image indicator and the corresponding standard value, and determine the ratio of the absolute error to the standard value. This ratio can be recorded as the score corresponding to each image indicator. The higher the score, the higher the image quality.

[0042] For example, the score for the spectral distribution in the image index can be calculated as follows: determine the standard value corresponding to each frequency band in the road segment image, calculate the absolute error corresponding to each frequency band, determine the ratio of the absolute error of each frequency band to the corresponding standard value, and this ratio is the score corresponding to each frequency band in the road segment image. Divide the sum of the scores corresponding to each frequency band by the number of frequency bands to calculate the average score corresponding to all frequency bands, and this average is the score for the spectral distribution.

[0043] S240. The reciprocals of each of the ratios are weighted and summed, or the reciprocal of the weighted sum of each of the ratios is determined as the overall image quality evaluation value.

[0044] Specifically, each ratio is assigned a corresponding weight. The reciprocals of each ratio can be summed with weights to obtain the overall image quality evaluation value. Alternatively, the reciprocal of the weighted sum of each ratio can be used to determine the overall image quality evaluation value, which can be proportional to the image quality of the road segment image. The weights corresponding to each ratio can be preset based on experience, and this invention does not impose any limitations on this.

[0045] For example, if the weight of the ratio corresponding to average brightness in the image metrics is 0.2, the weight of the ratio corresponding to contrast is 0.2, the weight of the ratio corresponding to average gradient is 0.4, and the weight of the ratio corresponding to spectral distribution is 0.2, then the overall image quality evaluation value can be expressed as the reciprocal of the weighted sum of each ratio, which is 1.

[0046] S250. Input the road segment image into the weather recognition model to obtain a weather array, wherein the weather array includes the confidence level corresponding to each weather condition.

[0047] In this embodiment, the weather array can be understood as the array output by the weather recognition model. The weather array can include the confidence scores of road segment images corresponding to different weather conditions. The weather array can be a floating-point array.

[0048] Specifically, the road segment image is input into the weather recognition model. The weather recognition model determines the confidence level of the road segment image for each type of weather and integrates all the confidence levels into an array for output. The output array is the weather array.

[0049] For example, weather classification could be: sunny or cloudy, but with water accumulation on the road surface; sunny or cloudy, but with snow accumulation on the road surface; light rain; heavy rain; light snow; heavy snow; dense fog; and others. The corresponding weather array output by the weather recognition model could be [0.67, 0.31, 0.22, 0.15, 0.09, 0.49, 0.26, 0.35].

[0050] S260. The weather corresponding to the highest confidence level in the weather array is determined as the weather indicated by the whole map weather information.

[0051] Specifically, the confidence scores in the weather array are sorted in descending order, and the weather corresponding to the highest confidence score is determined as the weather corresponding to the road segment image, which is the weather indicated by the weather information of the whole image.

[0052] For example, following the above embodiment, if the highest confidence level in the weather array is 0.67, and the corresponding weather category is "sunny or cloudy, but with water accumulation on the road", then the weather information of the whole image indicates that the weather of the road segment image is "sunny or cloudy, but with water accumulation on the road".

[0053] S270. If the overall map quality evaluation value is greater than the first threshold, the overall map quality evaluation value is mapped to a first value, and the product of the first value, the score value corresponding to the overall map weather information, and the confidence level of the overall map weather information is determined as the evaluation result, and S2100 is executed.

[0054] In this embodiment, the first threshold can be a preset threshold. When the overall image quality evaluation value is greater than the first threshold, it indicates that the image quality of the road segment is high and / or the road conditions of the corresponding traffic segment are poor. In this case, it is necessary to inspect the traffic segment corresponding to the image. The first value can be the value of the overall image quality evaluation value. When the overall image quality evaluation value is greater than the first threshold, the overall image quality evaluation value is mapped to the first value, which can be 1. The score value can be the quantitative score corresponding to the weather information of the overall image. The score value can be the weight of the weather information of the overall image. Different weather conditions can correspond to different score values.

[0055] Specifically, if the overall map quality evaluation value is greater than the first threshold, the overall map quality evaluation value is mapped to the first value. At this time, the evaluation result can be expressed as the product of the first value, the score corresponding to the overall map weather information, and the confidence level corresponding to the overall map weather information.

[0056] For example, if the overall map quality evaluation value is 0.5 and the first threshold is 0.4, and the overall map quality evaluation value is greater than the first threshold, then the overall map quality evaluation value is mapped to 1. In this case, the weather information in the overall map is "sunny or cloudy, but with standing water on the road," with a corresponding confidence level of 0.8 and a corresponding score of 0.9. The evaluation result can then be expressed as follows: .

[0057] S280. If the overall map quality evaluation value is less than the second threshold, the overall map quality evaluation value is mapped to a second value, and the product of the second value, the score corresponding to the overall map weather information, and the confidence level of the overall map weather information is determined as the evaluation result. If the second value is less than the first value and the second threshold is less than the first threshold, proceed to S2100.

[0058] In this embodiment, the second threshold can be a preset threshold for judging image quality. If the overall image quality evaluation value is less than the second threshold, it indicates that the image quality of the corresponding road segment is poor. The second threshold is less than the first threshold. The second value can be the value of the overall image quality evaluation value when the overall image quality evaluation value is less than the second threshold. The second value can be 0.

[0059] Specifically, if the overall map quality assessment value is less than the second threshold, then the overall map quality assessment value is mapped to the second value. The evaluation result can then be expressed as the product of the second value, the score corresponding to the overall map weather information, and the confidence level corresponding to the overall map weather information.

[0060] For example, the second value can be 0, in which case the evaluation result is 0, and the quality of the road segment image is poor.

[0061] S290. If the overall image quality evaluation value is not less than the second threshold and not greater than the first threshold, then the road segment image is divided into multiple sub-images, and the local quality evaluation value and local weather information of each sub-image are determined. Based on the local quality evaluation value and the local weather information, the evaluation result of the sub-image is determined.

[0062] In this embodiment, a sub-image can be a sub-image of a road segment image. A road segment image can be divided into multiple sub-images. The road segment image can be divided into grids according to pixel size, and the image within each grid is a sub-image. The local quality assessment value can be understood as a quantitative evaluation result of the image quality of a sub-image. Each sub-image can correspond to a unique local quality assessment value. The method for determining the local quality assessment value can be consistent with the method for determining the overall image quality assessment value. Local weather information can be the weather information corresponding to the sub-image. The method for determining the local weather information can be consistent with the method for determining the overall image weather information.

[0063] Specifically, during road patrols, due to the large field of view and wide acquisition range, different locations within the same road segment image may exhibit varying image quality or road conditions affected by weather. To improve road patrol efficiency, as much content as possible should be retained from the road segment image, provided the overall image quality is acceptable. Specifically, if the overall image quality evaluation value falls between the second and first thresholds, the road segment image is divided into multiple sub-images. The local quality evaluation value and local weather information for each sub-image are then determined. Based on these local quality evaluation values ​​and local weather information, an evaluation result for each sub-image is determined. Whether the evaluation result should be reported depends on whether it exceeds a preset threshold, thus preserving as much content as possible from the road segment image.

[0064] For example, if the first threshold is 0.4, the second threshold is 0.2, and the overall image quality evaluation value of the road segment image is 0.3, which falls between the second and first thresholds, then the road segment image is divided into a 3x3 grid of equal pixel size, with each grid containing a sub-image. If the local quality evaluation value of a certain sub-image is 0.9, which is greater than the first threshold, and the local weather information indicates "sunny or cloudy, but with water accumulation on the road surface," with a weight of 0.9 for the local weather information, then the evaluation result of the sub-image can be expressed as the product of the local quality evaluation value, confidence level, and score, which is 0.81.

[0065] For example, if the local quality evaluation value of a sub-image is 0.9, which is greater than the first threshold of 0.4, the local quality evaluation value of the sub-image can be mapped to 1.0; if the local quality evaluation value of a sub-image is 0.2, which is less than the second threshold of 0.3, the local quality evaluation value of the sub-image can be mapped to 0, and the evaluation result of the sub-image can be determined based on the mapped local quality evaluation value and local weather information.

[0066] For example, Figure 4 This is a flowchart of an image quality evaluation method for sub-images provided in an embodiment of the present invention. All sub-images are traversed one by one to determine the local quality evaluation value and local weather information corresponding to each sub-image, and the corresponding evaluation result is determined.

[0067] Optionally, determining the evaluation result of the sub-image based on the local quality evaluation value and the local weather information includes: The evaluation result is determined by multiplying the local quality evaluation value, the score corresponding to the local weather information, and the confidence level corresponding to the local weather information.

[0068] Specifically, the evaluation result of a sub-image can be represented as the product of a local quality evaluation value, a score corresponding to local weather information, and a confidence level corresponding to local weather information. The local quality evaluation value can be mapped to a specific numerical value based on the quantitative relationship between the local quality evaluation value and the first and second thresholds. This mapping method can be consistent with the mapping method for the overall image quality evaluation value.

[0069] S2100, Determine whether the evaluation result is greater than the set threshold.

[0070] In this embodiment, the threshold can be a preset threshold for determining whether an evaluation result should be reported. The threshold can be set based on experience or determined based on the statistics of historically reported evaluation results; this invention does not impose any limitations on this.

[0071] Specifically, the evaluation result is compared with a set threshold to determine whether the evaluation result is greater than the set threshold.

[0072] S2110. If so, report the information, including the evaluation results and the road segment images.

[0073] Specifically, if the evaluation result exceeds the set threshold, the evaluation result and road segment image will be encapsulated and compressed, for example, encapsulated and compressed into a JSON format data packet, and then reported via wired or wireless network. The reporting target can be a cloud server, etc.

[0074] For example, Figure 5 This is a flowchart of another image quality evaluation method provided by an embodiment of the present invention. First, the overall image quality evaluation value and overall weather information of the road segment image are calculated. If the overall image quality evaluation value is greater than a first threshold, it is mapped to a first value, and the road segment image is directly reported. If the overall image quality evaluation value is less than a second threshold, it is mapped to a second value, and the road segment image is not reported. If the overall image quality evaluation value is neither greater than the second threshold nor less than the first threshold, the road segment image is divided into multiple sub-images, and the local quality evaluation value and local weather information corresponding to each sub-image are calculated. The evaluation result corresponding to each sub-image is determined based on the local quality evaluation value and local weather information.

[0075] The technical solution of this invention involves: acquiring a road segment image; determining multiple image indicators of the road segment image; for each image indicator, determining the absolute error between the image indicator and the corresponding standard value, and determining the ratio of the absolute error to the corresponding standard value; weighted summing of each ratio to determine the overall image quality evaluation value; inputting the road segment image into a weather recognition model to obtain a weather array, the weather array including the confidence level corresponding to each weather condition; determining the weather condition corresponding to the highest confidence level in the weather array as the weather condition indicated by the overall image weather information; determining the quantitative relationship between the overall image quality evaluation value and a first threshold and a second threshold, mapping the overall image quality evaluation value according to the quantitative relationship, or dividing the road segment image into multiple sub-images, determining the local quality evaluation value and local weather information of each sub-image, and determining the evaluation result based on the local quality evaluation value and local weather information of the sub-images; determining whether the evaluation result is greater than a set threshold; if so, reporting the information, the reported information including the evaluation result and the road segment image. The technical solution of this invention standardizes and refines quality assessment by first determining image indicators, then determining the absolute error corresponding to the image indicators, and finally weighting and summing the ratios of the absolute errors to standard values ​​to determine the overall image quality evaluation value. By converting the absolute error into a ratio to the standard value, the influence of differences in the dimensions and numerical ranges of different image indicators is eliminated. By inputting road segment images into a weather recognition model, a weather array is obtained, including the confidence scores for various weather conditions. The weather with the highest confidence score is determined as the weather indicated by the overall image weather information. Outputting the confidence scores for various weather conditions by outputting the weather array simplifies the weather recognition logic of the weather recognition model and improves the efficiency of weather recognition. By first determining the overall image quality evaluation value of the road segment image, and then determining whether to divide the road segment image into sub-images based on the numerical range of the overall image quality evaluation value, and determining the corresponding evaluation results, specific analysis of the sub-images aims to retain as much usable information as possible in the road segment image, thereby avoiding excessive impact on inspection efficiency.

[0076] The present invention will be described by way of example below: Road patrol is a crucial step in ensuring road safety and smooth traffic flow. Vision-based road patrol technology can significantly improve patrol efficiency and has become a current application hotspot. However, vision-based technologies rely heavily on image quality, especially in rainy or snowy weather, where image quality deteriorates severely and may cause the algorithm to malfunction. Therefore, image quality evaluation has always been an important research topic.

[0077] Image quality assessment methods are mainly divided into two categories: objective assessment and subjective assessment. Objective assessment methods evaluate image quality by calculating various indicators, such as signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). These methods rely on the statistical properties of the image and can provide quantitative evaluation results.

[0078] Subjective evaluation methods rely on human visual assessment, typically employing comparative experiments where participants rate images of varying quality. This approach better reflects human perception of image quality. Furthermore, combining objective and subjective evaluation methods can yield even more accurate results.

[0079] Due to the complexity of road patrol scenarios, the large volume of data, and the rapid changes in the environment, even if patrol personnel notice changes in the image during the patrol, they cannot easily report these changes to the system, nor can they engage in fine-grained data interaction. Therefore, subjective evaluation methods are not suitable for road patrol scenarios, and a fully automated approach is necessary. Existing objective evaluation methods primarily rely on statistical values ​​such as image brightness and gradient, which are unsuitable for situations where road conditions have slightly deteriorated after light rain or snow, but the image quality itself remains good. These methods lack specificity for road patrol scenarios.

[0080] This invention proposes a method for evaluating road imaging quality in response to the impact of weather. This method combines image quality evaluation based on statistical analysis of image data (i.e., road segment images) with scene recognition technology based on neural networks. It can automatically identify weather conditions in images (i.e., road segment images) and assess image quality, thereby providing a reference for subsequent road condition identification.

[0081] In one example, a method for basic image quality assessment (i.e., overall image quality score) is provided, including: The basic image quality assessment mainly uses statistical assessment methods and adopts an overall assessment strategy followed by a regional assessment strategy (i.e., first determine the overall image quality assessment value, and then determine whether it is necessary to determine the local quality assessment value).

[0082] For example, image metrics include average brightness, which is the average of the pixel brightness values ​​within a region.

[0083] For example, image metrics include contrast, which describes the range of brightness variation of pixels within a region.

[0084] For example, image metrics include average gradient, which describes the sharpness of detail within a region.

[0085] For example, image metrics include spectral distribution. The Fourier transform is a mathematical method that converts a signal from the time domain to the frequency domain. It decomposes an image into a superposition of different frequency components and represents it as a spectrum. Calculating the Fourier transform of an acquired image (i.e., a road segment image) yields its spectrum, allowing for the statistical analysis of its spectral distribution. When image quality degrades, the spectral distribution also differs significantly from normal conditions. By comparing the current image's spectrum with a standard spectrum, the current image quality can be assessed.

[0086] For example, the method for determining the overall image quality evaluation value includes: for each of the above indicators, comparing the value calculated for the current image with the standard value for that type of scene, and calculating the relative error (i.e., the ratio of the absolute error to the standard value) to obtain the corresponding image quality score (i.e., the ratio).

[0087] In one example, a weather identification (i.e., determining weather information for an entire map) method is provided, including a weather identification model, training of the weather identification model, and output of the weather identification model.

[0088] For example, the weather recognition model is based on a neural network model, which contains basic units consisting of multiple convolutional layers, fully connected layers, and activation functions. The output size and number of channels of different basic units vary. They are connected in series to form a complete network. Depending on the hardware performance, the total number of basic units can be increased or decreased appropriately.

[0089] For example, the weather recognition model is trained using real-world scene data. Before training, the original images need to be labeled, including: overall weather conditions (sunny, cloudy, light rain, heavy rain, light snow, heavy snow, and fog / haze); overall road conditions (dry, puddles, and snow); and local image anomalies (puddles, snow-covered areas, and blurred areas). After labeling, the weather recognition model can be trained. In the actual workflow, misidentified images are gradually added to the dataset to further improve the accuracy of the weather recognition model.

[0090] For example, the output of the weather recognition model includes: according to the dataset definition, the original network output is a floating-point array, where each number (i.e., confidence level) corresponds to a weather condition in turn. The largest number represents the final result (i.e., the weather indicated by the weather information in the whole map).

[0091] In one example, a weight allocation method is provided, including: Each weather condition is assigned a corresponding score, as shown in Table 1. The scores can be adjusted based on the results in practical applications.

[0092] Table 1 Weather Score Based on this, the weights of the relative errors of the image indicators are determined. An example of the weight allocation method is shown in Table 2. In practical applications, the values ​​can be adjusted according to the effect. The weights of the relative errors can be found in Table 2. The overall image quality evaluation value can be determined by the reciprocal of the weighted sum of the relative errors, or by the weighted sum of the reciprocals of the relative errors.

[0093] Table 2 Weights of relative errors in image metrics The final score (i.e. the evaluation result) is the product of the weather-related score and the overall map quality evaluation score.

[0094] In addition, the mapping relationship of the scoring can be set specifically according to the actual situation. For example, when the overall image quality evaluation value is greater than a certain value (i.e., the first threshold), the current image (i.e., the road segment image) is considered to be a high-quality image, and its value is directly mapped to 1 (i.e., the first value), at which point only the influence of weather is considered; while when the overall image quality evaluation value is less than a certain value (i.e., the second threshold), the current image is considered to have no reference value, and its value is directly mapped to 0 (i.e., the second value), and the image is then discarded in the subsequent processing flow.

[0095] In one example, a total-to-score evaluation strategy is provided (i.e., first determining the evaluation result of the entire road segment image, and then determining the evaluation result of the sub-images as appropriate), including: The overall-to-subject evaluation strategy is adopted. First, the comprehensive quality index (i.e., the overall image quality evaluation value) is calculated for the global image (i.e., the road segment image). If the overall quality is slightly low but still within a reasonable range, the local quality index (i.e., the local quality evaluation value and local weather information) is calculated again to extract and save the recognition results of high-quality areas.

[0096] For example, the specific steps of the total-score evaluation strategy are as follows: Step 1: Input image data; Step 2: Calculate the overall map evaluation index (i.e., the overall map quality evaluation value) and weather (i.e., the overall map weather information); Step 3: If the overall image evaluation index is greater than the high-quality threshold (i.e., the first threshold), proceed to step 4; otherwise, proceed to step 5. Step 4: Set the overall map evaluation index to 1, and the current image to a high-quality image (i.e., the image of the reported road segment). Then proceed to step 9. Step 5: If the overall image evaluation index is less than the low quality threshold (i.e., the second threshold), proceed to step 6; otherwise, proceed to step 7. Step 6: Set the overall map evaluation index as follows The current image is a low-quality image (i.e., an image of a road segment that is not reported), proceed to step 9; Step 7: Divide the image into multiple sub-blocks; Step 8: For each sub-block in Step 7, calculate the local evaluation index (i.e., local quality evaluation value) and weather (i.e., local weather information), where, Number the sub-blocks; Step 9: Output the evaluation results and end.

[0097] For example, the detailed process of step 8 above includes: Step 1: Input each image sub-block (i.e., sub-image); Step 2: Let i = 1, where i is the i-th sub-image; Step 3: Calculate the image quality evaluation index (i.e., local quality evaluation value) and weather score (i.e., local weather information) of the i-th sub-block; Step 4: Let i = i + 1; Step 5: If i > total number of sub-blocks, proceed to step 6; otherwise, proceed to step 3. Step 6: Output all results for subsequent weighted calculation of recognition results; Step 7: End.

[0098] In one example, the overall image quality rating and score are multiplied as additional weights with the confidence level of the recognition result (i.e., the confidence level corresponding to weather conditions) to obtain the evaluation result.

[0099] In one example, an image quality assessment method is provided, including: Collect image data; identify weather conditions in the images (i.e., overall weather information); evaluate image quality (i.e., overall image quality evaluation value); fuse the image quality evaluation results and weather identification results; report the results, and if no report is made, upload location and other information to indicate that the road section has been inspected for defects.

[0100] The present invention has the following advantages: it can identify the weather conditions of the image, avoiding the problem that traditional statistical image evaluation indicators cannot accurately adapt to the patrol scenario; it integrates the image evaluation indicators with the recognition results, rather than two independent parts; it uses a total-to-part strategy to evaluate the image in blocks, retaining as much usable information as possible, thereby avoiding excessive impact on patrol efficiency.

[0101] This invention can identify weather conditions in captured images and evaluate image quality by combining weather information, thereby filtering and fusing the results of defect identification. Compared with traditional methods, this invention has advantages such as high automation, accurate evaluation, and better suitability to actual road patrol scenarios. It can be applied to various vision-based road patrol systems, effectively improving the accuracy of patrol result identification.

[0102] Example 3 Figure 6This is a schematic diagram of the structure of an image quality evaluation device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: The acquisition module 310 is used to acquire road segment images; The whole image quality evaluation value determination module 320 is used to analyze the pixels in the road segment image and determine the whole image quality evaluation value; The whole map weather information determination module 330 is used to determine the whole map weather information corresponding to the road segment image through a weather recognition model. The whole map weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image. The evaluation result determination module 340 is used to determine the evaluation result based on the overall map quality evaluation value and the overall map weather information.

[0103] The technical solution of this invention involves: acquiring road segment images via an acquisition module; determining an overall image quality evaluation value by analyzing pixels in the road segment images; determining an overall image weather information evaluation value by an overall image weather information determination module using a weather recognition model to determine the overall image weather information corresponding to the road segment images, whereby the overall image weather information indicates the weather and road conditions of the road segment corresponding to the road segment images; and determining an evaluation result module based on the overall image quality evaluation value and the overall image weather information to determine the evaluation result. By determining the overall image quality evaluation value and the overall image weather information, where the overall image weather information includes the weather and road conditions of the road segment corresponding to the road segment images, the analysis of road condition scenarios for each road segment avoids the problem of inaccurate evaluation of road conditions due to poor road conditions but good image quality. By jointly evaluating road segment images based on overall image weather information and overall image quality evaluation value, the accuracy of image quality assessment is improved, thereby providing a reference for subsequent road inspections.

[0104] In one embodiment, the evaluation result determination module 340 further includes: The first mapping unit is used to map the whole map quality evaluation value to a first value if the whole map quality evaluation value is greater than a first threshold, and to determine the evaluation result by multiplying the first value, the score value corresponding to the whole map weather information, and the confidence level of the whole map weather information. The second mapping unit is used to map the whole map quality evaluation value to a second value if the whole map quality evaluation value is less than a second threshold, and to determine the evaluation result by multiplying the second value, the score value corresponding to the whole map weather information, and the confidence level of the whole map weather information. The second value is less than the first value, and the second threshold is less than the first threshold. The segmentation unit is used to divide the road segment image into multiple sub-images if the overall image quality evaluation value is not less than a second threshold and not greater than a first threshold, determine the local quality evaluation value and local weather information of the sub-images respectively, and determine the evaluation result of the sub-images based on the local quality evaluation value and the local weather information.

[0105] In one embodiment, the partitioning unit is specifically used for: The evaluation result is determined by multiplying the local quality evaluation value, the score corresponding to the local weather information, and the confidence level corresponding to the local weather information.

[0106] In one embodiment, the whole image quality evaluation value determination module 320 is specifically used for: Determine multiple image metrics for the road segment image; For each image metric, determine the absolute error between the image metric and the corresponding standard value, and determine the ratio of the absolute error to the corresponding standard value; The reciprocal of the weighted sum of the aforementioned ratios is determined as the overall image quality evaluation value.

[0107] In one embodiment, the whole-map weather information determination module 330 is specifically used for: The road segment image is input into the weather recognition model to obtain a weather array, which includes the confidence level corresponding to each weather condition. The weather corresponding to the highest confidence level in the weather array is determined as the weather indicated by the whole map weather information.

[0108] In one embodiment, the device further includes: A determination module is used to determine whether the evaluation result is greater than a set threshold. The reporting module is used to report information if the condition is met. The reported information includes the evaluation results and the road segment images.

[0109] The image quality evaluation device provided in this embodiment of the invention can execute the image quality evaluation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0110] Example 4 Figure 7A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0111] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the methods proposed in this invention.

[0114] In some embodiments, the method proposed in this invention can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method proposed in this invention by any other suitable means (e.g., by means of firmware).

[0115] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of this invention, a computer-readable storage medium stores computer instructions that are used to cause a processor to execute and implement the method provided by this invention.

[0118] The present invention also provides a computer program product comprising a computer program that, when executed by a processor, implements the method provided according to embodiments of the present invention.

[0119] Computer-readable storage media can be tangible media that may contain or store computer programs for use by or in conjunction with an instruction execution system, apparatus, or device. Computer-readable storage media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0120] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or a liquid crystal display (LCD); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0121] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0122] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0123] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0124] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An image quality assessment method, characterized in that, include: Acquire road segment images; The pixels in the road segment image are analyzed to determine the overall image quality evaluation value; The weather recognition model determines the whole-map weather information corresponding to the road segment image, and the whole-map weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image; The evaluation result is determined based on the overall map quality evaluation value and the overall map weather information.

2. The method according to claim 1, characterized in that, The step of determining the evaluation result based on the overall map quality evaluation value and the overall map weather information includes: If the overall map quality evaluation value is greater than the first threshold, the overall map quality evaluation value is mapped to a first value, and the product of the first value, the score value corresponding to the overall map weather information, and the confidence level of the overall map weather information is determined as the evaluation result. If the overall map quality evaluation value is less than the second threshold, the overall map quality evaluation value is mapped to a second value, and the product of the second value, the score corresponding to the overall map weather information, and the confidence level of the overall map weather information is determined as the evaluation result. The second value is less than the first value, and the second threshold is less than the first threshold. If the overall image quality evaluation value is not less than the second threshold and not greater than the first threshold, then the road segment image is divided into multiple sub-images, and the local quality evaluation value and local weather information of each sub-image are determined. Based on the local quality evaluation value and the local weather information, the evaluation result of the sub-image is determined.

3. The method according to claim 2, characterized in that, Determining the evaluation result of the sub-image based on the local quality evaluation value and the local weather information includes: The evaluation result is determined by multiplying the local quality evaluation value, the score corresponding to the local weather information, and the confidence level corresponding to the local weather information.

4. The method according to claim 1, characterized in that, The step of determining the overall image quality evaluation value based on the road segment image includes: Determine multiple image metrics for the road segment image; For each image metric, determine the absolute error between the image metric and the corresponding standard value, and determine the ratio of the absolute error to the corresponding standard value; The weighted sum of the reciprocals of each of the ratios, or the reciprocal of the weighted sum of the ratios, is determined as the overall image quality evaluation value.

5. The method according to claim 1, characterized in that, The step of determining the overall weather information corresponding to the road segment image through a weather recognition model includes: The road segment image is input into the weather recognition model to obtain a weather array, which includes the confidence level corresponding to each weather condition. The weather corresponding to the highest confidence level in the weather array is determined as the weather indicated by the whole map weather information.

6. The method according to claim 1, characterized in that, After determining the evaluation result based on the overall map quality evaluation value and the overall map weather information, the process includes: Determine whether the evaluation result is greater than a set threshold; If so, information is reported, including the evaluation results and the road segment images.

7. An image quality evaluation device, characterized in that, include: The acquisition module is used to acquire images of road segments; The whole image quality evaluation value determination module is used to analyze the pixels in the road segment image and determine the whole image quality evaluation value; The whole map weather information determination module is used to determine the whole map weather information corresponding to the road segment image through a weather recognition model. The whole map weather information indicates the weather corresponding to the road segment image and the road conditions of the road segment corresponding to the road segment image. The evaluation result determination module is used to determine the evaluation result based on the overall map quality evaluation value and the overall map weather information.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method of any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images